Supercharge Your Innovation With Domain-Expert AI Agents!

An image-based cooking smoke detection method and smart smoke machine

A detection method and smoke technology, which is applied in the field of image analysis and smoke detection, can solve problems such as unrealizable, affecting background feature extraction, unstable smoke, etc., and achieve the effects of reducing interference, improving stability, and reducing complexity

Active Publication Date: 2022-02-01
JOYOUNG CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But this is only suitable for the scene of large smoke. For the cooking process, small smoke and unstable smoke that often appear are basically impossible to achieve.
[0004] 2. Judging by the optical flow detection method, the optical flow detection method applies the diffusion characteristics and motion characteristics of the smoke, but this method is not applicable in the cooking process, because the human motion amplitude characteristics are much higher than the smoke during the cooking process, and The motion properties of weak smoke are disturbed by image-forming noise
However, for different home environments, different lighting conditions, cooking process, and utensil placement will affect the extraction of background features.
thus it is difficult to provide a stable background feature
So this method is only suitable for strong smoke conditions

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An image-based cooking smoke detection method and smart smoke machine
  • An image-based cooking smoke detection method and smart smoke machine
  • An image-based cooking smoke detection method and smart smoke machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] Such as image 3 As shown, the smart cigarette machine described in this embodiment includes: a camera 100, an image processing unit 200, a control unit 300, and a drive unit 400. The camera 100 collects images in a preset cooking area in real time, and is controlled by the image processing unit 200 and The unit 300 analyzes and processes the collected images to determine the smoke concentration, and the driving unit 400 controls the speed of the smoke machine according to the smoke concentration.

[0095] The smoke detection workflow is as follows: Figure 4 Shown:

[0096] S1. First acquire images through the camera;

[0097] S2. Preprocess the input image, including cropping, filtering, scaling, and grayscale, and finally get a grayscale image of 300*300 pixels, such as Figure 5 as shown,

[0098] S3. It is more accurate to detect whether there is a pot through the deep neural network. In addition, because the scene of the cooking process is relatively fixed, a...

Embodiment 2

[0102] If the pot exists, you need to detect the smoke, and then output the presence of the pot and the corresponding smoke concentration.

[0103] Among them, the process of smoke detection is as follows: Figure 6 Shown:

[0104] Preprocess the input image, including cropping, filtering, scaling, and grayscale, and finally get a grayscale image of 300*300 pixels;

[0105] Gradient feature extraction is performed on the preprocessed image, such as Sobel gradient feature;

[0106] According to the characteristics of the scene in the cooking process, the background in the scene is unstable, but the pot must exist, so the gradient feature of the edge of the pot can be used as the basis for judging whether there is smoke, which has high adaptability. In this embodiment, it is For circular pots, the gradient data in the ring can be extracted for statistics. In order to reduce the interference of the user's cooking actions, the upper half of the ring is selected for histogram sta...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

This application proposes an image-based cooking smoke detection method and a smart hood, which relate to the field of image analysis smoke detection, including: collecting images in a preset cooking area; acquiring the pan when the image contains the pan The feature information of the edge area of ​​the cooking area; according to the feature information, the size of the smoke concentration in the cooking area is determined. The smoke density in the cooking area is determined by extracting the feature information of the edge area of ​​the pot from the collected images in the cooking area. According to the situation of the smoke rate, the speed of the control hood is adjusted in stages to realize the automatic control of the hood.

Description

technical field [0001] The invention relates to the field of image analysis smoke detection, in particular to an image-based cooking smoke detection method and an intelligent smoke machine. Background technique [0002] At present, there are several methods for image-based smoke detection: [0003] 1. Judging by the color, the R (red), G (green), and B (blue) components of the smoke are relatively concentrated and tend to be consistent; YUV represents an image format, Y represents brightness, U and V represent chroma; HIS It also represents an image format, I is intensity, and the change of Y component is basically the same as R, G, and B, but the U and V components will be reduced; the smoke is the color of the picture becomes lighter, so the saturation S will decrease, and the I component is R , the linear combination of G and B, so the change is basically: if the smoke is black, the I component will move to the direction of smaller pixels; if the smoke is gray and white,...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G01N15/06F24C15/20
Inventor 朱泽春魏乃科
Owner JOYOUNG CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com